state: generation 9222 (cycle)
This commit is contained in:
@@ -1745,7 +1745,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-18T11:35:11.181253+00:00",
|
||||
"generatedAt": "2026-09-18T11:38:05.594666+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 84,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -11,7 +11,7 @@
|
||||
"1": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 673,
|
||||
"listingErrors": 674,
|
||||
"nextPage": 1,
|
||||
"recordsScanned": 0,
|
||||
"uniqueRecords": 0
|
||||
@@ -102,12 +102,12 @@
|
||||
"cutoffAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"failureLogsInspected": 0,
|
||||
"mode": "incremental_decision_only",
|
||||
"nextAccountIndex": 1,
|
||||
"nextAccountIndex": 2,
|
||||
"recordsScanned": 0,
|
||||
"seenTaskIds": [],
|
||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"terminalRecords": 0,
|
||||
"uniqueRecords": 0,
|
||||
"updatedAt": "2026-09-18T11:35:11.156665+00:00",
|
||||
"updatedAt": "2026-09-18T11:38:05.568407+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,7 +416,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-18T11:33:38.718078+00:00",
|
||||
"generatedAt": "2026-09-18T11:36:19.365263+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-18T11:18:54.959201+00:00",
|
||||
"lastSyncTime": "2026-09-18T11:18:54.918111+00:00",
|
||||
"generatedAt": "2026-09-18T11:36:12.168347+00:00",
|
||||
"lastSyncTime": "2026-09-18T11:36:11.987002+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -2286,7 +2286,7 @@
|
||||
"decisionSuccessRate": 0.1615,
|
||||
"decisionTotal": 130,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 23,
|
||||
"ambiguous_runtime": 24,
|
||||
"framework_architecture_unsupported": 64,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 43,
|
||||
@@ -2295,18 +2295,18 @@
|
||||
"参数/模板问题": 3,
|
||||
"验证失败": 47
|
||||
},
|
||||
"failureCount": 183,
|
||||
"failureRate": 0.8971,
|
||||
"failureCount": 184,
|
||||
"failureRate": 0.8976,
|
||||
"framework": "unknown",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 21,
|
||||
"successRate": 0.1029,
|
||||
"successRate": 0.1024,
|
||||
"targetGpu": "Iluvatar_mrv-100",
|
||||
"taskType": "text-generation",
|
||||
"total": 204,
|
||||
"unresolvedFailureCount": 73
|
||||
"total": 205,
|
||||
"unresolvedFailureCount": 74
|
||||
},
|
||||
"Iluvatar_mrv-100|vllm|text-generation": {
|
||||
"attributableFailureCount": 11,
|
||||
@@ -2821,7 +2821,7 @@
|
||||
"decisionSuccessRate": 0.2685,
|
||||
"decisionTotal": 257,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 163,
|
||||
"ambiguous_runtime": 164,
|
||||
"backend_operator": 4,
|
||||
"framework_architecture_unsupported": 126,
|
||||
"memory_capacity": 5,
|
||||
@@ -2832,15 +2832,15 @@
|
||||
"参数/模板问题": 73,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1098,
|
||||
"failureCount": 1099,
|
||||
"failureRate": 0.9409,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 69,
|
||||
"successRate": 0.0591,
|
||||
"total": 1167,
|
||||
"unresolvedFailureCount": 909
|
||||
"total": 1168,
|
||||
"unresolvedFailureCount": 910
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 412,
|
||||
@@ -2979,7 +2979,7 @@
|
||||
"unresolvedFailureCount": 17
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-18T11:18:54.953778+00:00",
|
||||
"generatedAt": "2026-09-18T11:36:12.163120+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 58,
|
||||
@@ -3151,7 +3151,7 @@
|
||||
"decisionSuccessRate": 0.1549,
|
||||
"decisionTotal": 142,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 25,
|
||||
"ambiguous_runtime": 26,
|
||||
"framework_architecture_unsupported": 74,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 44,
|
||||
@@ -3160,15 +3160,15 @@
|
||||
"参数/模板问题": 3,
|
||||
"验证失败": 47
|
||||
},
|
||||
"failureCount": 196,
|
||||
"failureRate": 0.8991,
|
||||
"failureCount": 197,
|
||||
"failureRate": 0.8995,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 22,
|
||||
"successRate": 0.1009,
|
||||
"total": 218,
|
||||
"unresolvedFailureCount": 75
|
||||
"successRate": 0.1005,
|
||||
"total": 219,
|
||||
"unresolvedFailureCount": 76
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"attributableFailureCount": 1,
|
||||
@@ -7653,19 +7653,19 @@
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"Iluvatar_bi-150|vllm|text-generation": {
|
||||
"attributableFailureCount": 10,
|
||||
"consecutiveFailures": 10,
|
||||
"attributableFailureCount": 9,
|
||||
"consecutiveFailures": 9,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 10,
|
||||
"decisionTotal": 9,
|
||||
"failureBreakdown": {
|
||||
"backend_operator": 1,
|
||||
"framework_architecture_unsupported": 5,
|
||||
"model_load": 3,
|
||||
"model_load": 2,
|
||||
"repository_structure": 1
|
||||
},
|
||||
"failureCount": 10,
|
||||
"failureCount": 9,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -7677,19 +7677,19 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_bi-150",
|
||||
"taskType": "text-generation",
|
||||
"total": 10,
|
||||
"total": 9,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Iluvatar_mrv-100|unknown|text-generation": {
|
||||
"attributableFailureCount": 13,
|
||||
"attributableFailureCount": 12,
|
||||
"consecutiveFailures": 1,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 0.6842,
|
||||
"decisionSuccessRate": 0.3158,
|
||||
"decisionTotal": 19,
|
||||
"decisionFailureRate": 0.6667,
|
||||
"decisionSuccessRate": 0.3333,
|
||||
"decisionTotal": 18,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"framework_architecture_unsupported": 11,
|
||||
"model_load": 1,
|
||||
"tokenizer_compatibility": 1,
|
||||
"参数/模板问题": 1
|
||||
},
|
||||
@@ -7697,7 +7697,7 @@
|
||||
"failureRate": 0.7,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-17T14:39:04.244134+00:00",
|
||||
"lastTerminalAt": "2026-09-18T11:36:11.987002+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -7706,7 +7706,7 @@
|
||||
"targetGpu": "Iluvatar_mrv-100",
|
||||
"taskType": "text-generation",
|
||||
"total": 20,
|
||||
"unresolvedFailureCount": 1
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"Kunlunxin_p-800|unknown|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -14337,15 +14337,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 2248,
|
||||
"totalRecords": 2351,
|
||||
"terminalRecords": 2249,
|
||||
"totalRecords": 2352,
|
||||
"totals": {
|
||||
"attributableFailureCount": 731,
|
||||
"decisionFailureRate": 0.8431,
|
||||
"decisionSuccessRate": 0.1569,
|
||||
"decisionTotal": 867,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 564,
|
||||
"ambiguous_runtime": 565,
|
||||
"backend_operator": 55,
|
||||
"framework_architecture_unsupported": 482,
|
||||
"memory_capacity": 12,
|
||||
@@ -14357,15 +14357,15 @@
|
||||
"参数/模板问题": 133,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 2112,
|
||||
"failureCount": 2113,
|
||||
"failureRate": 0.9395,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 11,
|
||||
"successCount": 136,
|
||||
"successRate": 0.0605,
|
||||
"total": 2248,
|
||||
"unresolvedFailureCount": 1370
|
||||
"total": 2249,
|
||||
"unresolvedFailureCount": 1371
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
@@ -14405,6 +14405,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 2351,
|
||||
"summarizedRecords": 2352,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-18T11:36:11.987002+00:00", "modelId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-18T11:29:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4610408", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm", "lastSyncTime": "2026-09-18T08:57:11.697973+00:00", "modelId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-18T08:51:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4490562", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-18T05:37:23.595667+00:00", "modelId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-18T05:33:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4458008", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-18T04:07:34.207962+00:00", "modelId": "BAAI/Aerospace-llama3_1_8B_instruct", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-18T03:59:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4471933", "taskType": "text-generation", "verifyResult": -1}
|
||||
@@ -297,4 +298,3 @@
|
||||
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-12T02:48:11.158114+00:00", "modelId": "RedHatAI/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T02:43:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4458009", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-12T02:39:29.219599+00:00", "modelId": "RedHatAI/Qwen2.5-3B-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T02:39:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4100876", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["mellum"], "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-12T02:39:29.219629+00:00", "modelId": "JetBrains/Mellum2-12B-A2.5B-Thinking", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T02:35:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4152611", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-12T02:30:20.417896+00:00", "modelId": "nightmedia/Qwen3-4B-Thinking-2507-Gemini-3-Pro-Preview-High-Reasoning-Distill-Heretic-qx86-hi-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T02:27:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4079970", "taskType": "text-generation", "verifyResult": -1}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user